© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68743
    Prev
    Next
    INDEX
    Explanations

    open parenthesis

    np_max-act · gemini-2.0-flash

    This neuron detects JavaScript DOM‐selection calls, particularly occurrences of document.getElementById (and its associated element‐ID strings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oklyn
    -0.06
     Xem
    -0.06
     java
    -0.06
     BA
    -0.06
    lapping
    -0.06
     CSR
    -0.06
    .latitude
    -0.06
     ألف
    -0.06
     XS
    -0.06
    粗
    -0.06
    POSITIVE LOGITS
    kos
    0.07
    化
    0.06
     relaciones
    0.06
     wrongdoing
    0.06
     modification
    0.06
    getElement
    0.06
     excitement
    0.06
    šker
    0.06
     distortion
    0.06
     nghiên
    0.06
    Activations Density 0.005%

    No Known Activations